Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 13851
    Prev
    Next
    INDEX
    Explanations

    words related to saving or preserving something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "save" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ferdinand
    -0.61
     fluor
    -0.58
     earliest
    -0.57
    LESS
    -0.56
     numbered
    -0.56
     reflective
    -0.56
     molded
    -0.55
    xy
    -0.55
     brewed
    -0.54
     waning
    -0.53
    POSITIVE LOGITS
    aves
    1.21
    aved
    1.09
    ajor
    0.89
    anty
    0.84
    aneers
    0.83
    ave
    0.81
    veyard
    0.81
    aving
    0.81
    nesday
    0.80
    ignt
    0.80
    Activations Density 0.005%

    No Known Activations